{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/towards-compositional-adversarial-robustness","title":"Towards Compositional Adversarial Robustness: Generalizing Adversarial Training to Composite Semantic Perturbations","arxiv_id":"2202.04235","date":"2022-02-09","proceeding":"CVPR 2023 1","authors":["Lei Hsiung","Yun-Yun Tsai","Pin-Yu Chen","Tsung-Yi Ho"],"abstract":"Model robustness against adversarial examples of single perturbation type such as the $\\ell_{p}$-norm has been widely studied, yet its generalization to more realistic scenarios involving multiple semantic perturbations and their composition remains largely unexplored. In this paper, we first propose a novel method for generating composite adversarial examples. Our method can find the optimal attack composition by utilizing component-wise projected gradient descent and automatic attack-order scheduling. We then propose generalized adversarial training (GAT) to extend model robustness from $\\ell_{p}$-ball to composite semantic perturbations, such as the combination of Hue, Saturation, Brightness, Contrast, and Rotation. Results obtained using ImageNet and CIFAR-10 datasets indicate that GAT can be robust not only to all the tested types of a single attack, but also to any combination of such attacks. GAT also outperforms baseline $\\ell_{\\infty}$-norm bounded adversarial training approaches by a significant margin.","url_abs":"https://arxiv.org/abs/2202.04235v3","url_pdf":"https://arxiv.org/pdf/2202.04235v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"towards-compositional-adversarial-robustness","repo_url":"https://github.com/IBM/composite-adv","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"adversarial-robustness","task_name":"Adversarial Robustness"},{"task_slug":"scheduling","task_name":"Scheduling"}],"methods":[{"method_slug":"gat","method_name":"GAT"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2202.04235","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}